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

    Neuronpedia

    INDEX
    Explanations

    words related to consent and acceptance in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agues
    -0.17
    chedulers
    -0.15
     Armour
    -0.15
    .sap
    -0.15
    olec
    -0.14
    piler
    -0.14
    entlich
    -0.14
    .bunifuFlatButton
    -0.13
     Conv
    -0.13
    أس
    -0.13
    POSITIVE LOGITS
    ONGL
    0.17
    491
    0.14
    611
    0.14
     redhead
    0.14
    432
    0.14
    airo
    0.13
    ASI
    0.13
    she
    0.13
    entin
    0.13
    er
    0.13
    Act Density 0.007%

    No Known Activations