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

    Neuronpedia

    INDEX
    Explanations

    instances where the text signals that none of a set of options are applicable or relevant

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lished
    -0.55
    bledon
    -0.54
     srf
    -0.53
     widest
    -0.53
     turf
    -0.53
     drift
    -0.53
     seas
    -0.52
     Drift
    -0.51
     descent
    -0.51
     Beir
    -0.51
    POSITIVE LOGITS
    conom
    1.25
    lect
    0.93
    theless
    0.91
    ffect
    0.87
    galitarian
    0.85
    except
    0.84
    uther
    0.82
    essee
    0.79
    etting
    0.78
    lust
    0.77
    Act Density 0.023%

    No Known Activations