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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Collins."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Collins."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.75
     discrep
    -0.73
    inished
    -0.70
    cgi
    -0.69
    ilitation
    -0.69
    ETA
    -0.68
    ocard
    -0.67
    fare
    -0.65
    ãĥ¤
    -0.65
    hyp
    -0.63
    POSITIVE LOGITS
    worth
    1.12
     Collins
    0.98
    mount
    0.84
    ville
    0.81
    ively
    0.79
     Andersen
    0.79
    Collins
    0.75
    ision
    0.73
    ynski
    0.72
    creen
    0.71
    Act Density 0.011%

    No Known Activations