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

    Neuronpedia

    INDEX
    Explanations

    words related to neighborhoods and livability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idle
    -0.16
    adge
    -0.15
    olidays
    -0.14
    ÏĥÏĦα
    -0.14
     Legend
    -0.14
    Ñıж
    -0.14
    iв
    -0.14
    .Invariant
    -0.14
    ollider
    -0.13
    .Cascade
    -0.13
    POSITIVE LOGITS
     Chin
    0.16
    amen
    0.15
    illy
    0.15
    771
    0.15
    iel
    0.14
    AKE
    0.14
    æķı
    0.13
    дÑĥ
    0.12
    umer
    0.12
     zf
    0.12
    Act Density 0.178%

    No Known Activations