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

    Neuronpedia

    INDEX
    Explanations

    words related to completing tasks or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "finish" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hare
    -0.69
    uli
    -0.68
    arov
    -0.67
    Origin
    -0.66
    orum
    -0.65
    elled
    -0.65
    arth
    -0.64
    cot
    -0.63
    esis
    -0.63
    iji
    -0.63
    POSITIVE LOGITS
     touches
    0.82
     off
    0.68
     unfinished
    0.67
    ãĤ¤ãĥĪ
    0.65
     up
    0.64
     College
    0.64
     compiling
    0.64
     composing
    0.62
     packing
    0.62
     runner
    0.62
    Act Density 0.036%

    No Known Activations