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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or activity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    agna
    -0.67
    osterone
    -0.66
    imov
    -0.65
     Wing
    -0.65
    STE
    -0.64
     Infantry
    -0.64
    ossibility
    -0.63
    fulness
    -0.63
     anonymity
    -0.61
     homophobia
    -0.60
    POSITIVE LOGITS
     greet
    0.76
     haunt
    0.69
     conquer
    0.69
    leans
    0.68
     boarded
    0.67
     ruin
    0.66
     shove
    0.66
    orian
    0.66
    oggles
    0.64
     greets
    0.64
    Act Density 0.061%

    No Known Activations