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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal and ethical issues

    oai_token-act-pair · gpt-3.5-turbo

    references to a sense of belonging or community involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RI
    -0.65
     overheard
    -0.61
     Advisory
    -0.61
     cue
    -0.61
    ioxide
    -0.59
     Explosion
    -0.59
     pointers
    -0.57
    Untitled
    -0.57
     Screen
    -0.57
     countdown
    -0.56
    POSITIVE LOGITS
    ously
    1.07
    ingly
    1.03
    ment
    0.96
    liest
    0.96
    enment
    0.92
    ably
    0.91
    itude
    0.90
    iously
    0.90
    erous
    0.89
    ienced
    0.89
    Act Density 0.181%

    No Known Activations