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

    Neuronpedia

    INDEX
    Explanations

    words related to indication or signaling actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    farlane
    -0.70
    wn
    -0.65
    repos
    -0.64
    tw
    -0.63
     Rowe
    -0.60
    al
    -0.59
    forbes
    -0.59
    пло
    -0.59
    zlib
    -0.58
    forgotten
    -0.57
    POSITIVE LOGITS
     INDIC
    1.65
     Indicates
    1.52
     indicators
    1.44
    Indicates
    1.42
     Indicators
    1.41
     indicates
    1.39
     Indicator
    1.36
     indicated
    1.36
     indicate
    1.35
    indicates
    1.35
    Act Density 0.140%

    No Known Activations