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

    Neuronpedia

    INDEX
    Explanations

    words related to political entities or affiliations

    oai_token-act-pair · gpt-3.5-turbo

    terminologies related to representation and identity within specific groups or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.84
     icing
    -0.70
     sidx
    -0.64
    vent
    -0.64
    terness
    -0.63
    thood
    -0.61
     Canaver
    -0.60
     Kissinger
    -0.60
     theorem
    -0.60
     Verb
    -0.58
    POSITIVE LOGITS
    ét
    0.72
    ild
    0.66
    erville
    0.66
    etts
    0.65
    emouth
    0.62
    urg
    0.60
    anded
    0.60
    iciary
    0.60
    olulu
    0.59
    AL
    0.59
    Act Density 0.123%

    No Known Activations