Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to diversion or deviation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to divergence and differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.22
    3:0.07
    4:0.22
    5:0.04
    6:0.03
    7:0.04
    8:0.08
    9:0.09
    10:0.05
    11:0.02
    Negative Logits
     sarcast
    -1.43
    Hunt
    -1.32
    �
    -1.31
     proudly
    -1.23
    Fax
    -1.18
    kinson
    -1.15
     nostalg
    -1.14
     showc
    -1.10
    Buzz
    -1.10
    aeper
    -1.09
    POSITIVE LOGITS
     BST
    1.26
     wavelength
    1.25
    ilial
    1.23
    ulty
    1.22
    ministic
    1.20
     Yen
    1.20
    ateral
    1.19
    imensional
    1.19
     \(
    1.19
     \(\
    1.17
    Act Density 0.004%

    No Known Activations