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

    Neuronpedia

    INDEX
    Explanations

    terms related to suspicion and trust issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gressor
    -0.17
    icens
    -0.16
    asha
    -0.16
    ILON
    -0.15
    ë¦
    -0.15
    uent
    -0.15
    elin
    -0.15
     Leban
    -0.14
    umba
    -0.14
    asurer
    -0.14
    POSITIVE LOGITS
    oot
    0.18
    ienes
    0.15
    ably
    0.15
    ively
    0.14
    itably
    0.14
    .om
    0.13
    296
    0.13
    IMA
    0.13
     anno
    0.13
     Monk
    0.13
    Act Density 0.044%

    No Known Activations