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

    Neuronpedia

    INDEX
    Explanations

    the prefix "cor" followed by various suffixes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hits
    -0.74
    icans
    -0.71
     Hunters
    -0.70
     Rutherford
    -0.67
    TPS
    -0.65
     Wanted
    -0.63
    Known
    -0.63
    lihood
    -0.62
    éĹĺ
    -0.61
     Finder
    -0.61
    POSITIVE LOGITS
    porate
    1.47
    ridor
    1.32
    rection
    1.24
    poral
    1.19
    ruption
    1.18
    por
    1.15
    respond
    1.11
    rupted
    1.11
    rupt
    1.07
    pse
    1.01
    Act Density 0.026%

    No Known Activations