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

    Neuronpedia

    INDEX
    Explanations

    phrases related to games of hide-and-seek and related activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ical
    -0.79
    juven
    -0.71
    sole
    -0.69
    hered
    -0.68
    STER
    -0.68
    biology
    -0.66
    bidden
    -0.66
    enough
    -0.66
    nikov
    -0.65
     Helpful
    -0.65
    POSITIVE LOGITS
    tackle
    0.90
     Conquer
    0.90
    rew
    0.73
     discard
    0.72
     Replace
    0.70
     scratch
    0.69
     tumble
    0.69
     reuse
    0.69
     disposal
    0.68
     scramble
    0.68
    Act Density 0.173%

    No Known Activations