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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing the emotional state and evaluation of experiences or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.47
    3:0.11
    4:0.08
    5:0.03
    6:0.05
    7:0.04
    8:0.03
    9:0.02
    10:0.05
    11:0.04
    Negative Logits
    vati
    -1.63
     shelters
    -1.60
    itaire
    -1.48
    ablo
    -1.43
     fasting
    -1.41
     tirelessly
    -1.41
    tty
    -1.33
     vulner
    -1.32
     Barron
    -1.31
     sacrific
    -1.29
    POSITIVE LOGITS
     signifies
    1.71
     outwe
    1.63
     nutshell
    1.53
    tones
    1.51
     illustrates
    1.49
     Pearce
    1.48
    mean
    1.47
    IRD
    1.38
    ◼
    1.37
     indicates
    1.35
    Act Density 0.118%

    No Known Activations