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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to evaluations of reports and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deterior
    -0.15
    assel
    -0.15
    arrow
    -0.14
    eless
    -0.14
    olatile
    -0.13
    ergus
    -0.13
    encion
    -0.13
    orrow
    -0.13
    itched
    -0.13
    สล
    -0.13
    POSITIVE LOGITS
     over
    0.77
    Over
    0.63
     Over
    0.62
    over
    0.59
     OVER
    0.57
    -over
    0.56
    _over
    0.53
    è¿ĩ
    0.52
    .over
    0.52
     overs
    0.51
    Act Density 0.322%

    No Known Activations