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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical contact or proximity between objects or individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of physical interactions or closeness between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audi
    -0.68
    Bey
    -0.68
    brew
    -0.66
    iac
    -0.65
    Rum
    -0.63
    Online
    -0.63
    FY
    -0.62
    icter
    -0.62
    ARS
    -0.62
    ONSORED
    -0.61
    POSITIVE LOGITS
     holes
    0.89
     corners
    0.89
     unprotected
    0.77
     uneven
    0.77
     shoulder
    0.73
     bushes
    0.72
     edges
    0.71
     securely
    0.71
     densely
    0.71
     snug
    0.70
    Act Density 0.293%

    No Known Activations