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

    Neuronpedia

    INDEX
    Explanations

    ways or methods of doing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.72
    avorite
    -0.69
    inently
    -0.68
    rament
    -0.67
     reload
    -0.66
     bluff
    -0.63
     Fishing
    -0.62
    inally
    -0.62
    anmar
    -0.62
    itialized
    -0.62
    POSITIVE LOGITS
    WARD
    0.78
    finding
    0.77
    ward
    0.72
     Affect
    0.71
    fare
    0.70
     resembling
    0.69
     reminiscent
    0.69
    hered
    0.68
     resembles
    0.67
    sid
    0.66
    Act Density 0.036%

    No Known Activations