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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "collaborate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃch
    -0.18
    eba
    -0.17
    umas
    -0.16
    resas
    -0.15
    isbury
    -0.15
    nila
    -0.14
    rus
    -0.14
    ldre
    -0.14
     Marino
    -0.14
    unken
    -0.14
    POSITIVE LOGITS
    ative
    0.36
    atively
    0.28
    ators
    0.25
    atory
    0.25
    ator
    0.23
    ativ
    0.23
    ATIVE
    0.22
    er
    0.21
    ate
    0.21
    abor
    0.21
    Act Density 0.006%

    No Known Activations