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

    Neuronpedia

    INDEX
    Explanations

    emotionally charged phrases and concepts related to personal relationships and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omm
    -0.16
    gaard
    -0.15
    673
    -0.15
    LEGRO
    -0.15
    ñana
    -0.15
    pollo
    -0.15
    bsolute
    -0.15
    asca
    -0.15
    ansson
    -0.14
    رس
    -0.14
    POSITIVE LOGITS
    itan
    0.18
    ä½į
    0.15
    ambio
    0.14
     vys
    0.14
    ien
    0.14
    .Aggressive
    0.14
    aria
    0.13
    averse
    0.13
    each
    0.13
     Stick
    0.13
    Act Density 1.769%

    No Known Activations