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

    Neuronpedia

    INDEX
    Explanations

    phrases that establish a connection or response between people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orm
    -0.15
     ifndef
    -0.14
    OTH
    -0.14
     htons
    -0.14
    graduate
    -0.14
    FTA
    -0.13
    uer
    -0.13
    ive
    -0.13
    omba
    -0.13
    ync
    -0.13
    POSITIVE LOGITS
     sit
    0.20
     sits
    0.19
    gos
    0.17
     lies
    0.15
    mlin
    0.15
     stands
    0.15
     sat
    0.15
     go
    0.15
    ValuePair
    0.14
    rafted
    0.14
    Act Density 0.018%

    No Known Activations