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

    Neuronpedia

    INDEX
    Explanations

    phrases related to citing information from sources

    oai_token-act-pair · gpt-3.5-turbo

    references to external reports or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.69
    iously
    -0.64
    earth
    -0.63
    assed
    -0.63
    ulz
    -0.63
    rou
    -0.62
     crunch
    -0.60
     extras
    -0.59
    selves
    -0.58
     oily
    -0.58
    POSITIVE LOGITS
     however
    1.10
     albeit
    0.86
     although
    0.82
     meanwhile
    0.80
    Downloadha
    0.78
     moreover
    0.76
    raints
    0.76
     though
    0.73
     huh
    0.71
     according
    0.69
    Act Density 1.237%

    No Known Activations