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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or enhancement in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.06
    4:0.13
    5:0.02
    6:0.05
    7:0.36
    8:0.03
    9:0.03
    10:0.07
    11:0.04
    Negative Logits
    event
    -1.45
     Feast
    -1.42
    input
    -1.40
     Signed
    -1.39
     archived
    -1.38
     guiActiveUnfocused
    -1.38
     rotting
    -1.37
    da
    -1.37
    updated
    -1.35
    efe
    -1.35
    POSITIVE LOGITS
     understanding
    1.86
    uggest
    1.84
     redef
    1.78
     furthe
    1.75
     estab
    1.61
     misunderstand
    1.59
     stereotypes
    1.56
    VIS
    1.55
    ixel
    1.55
     embraces
    1.53
    Act Density 0.004%

    No Known Activations