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

    Neuronpedia

    INDEX
    Explanations

    terms related to instinct and intuition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oose
    -0.16
    efs
    -0.16
    edula
    -0.16
    dued
    -0.15
    ween
    -0.15
    hurst
    -0.15
    .builder
    -0.14
    esty
    -0.14
    але
    -0.14
    pez
    -0.14
    POSITIVE LOGITS
    inst
    0.17
    inn
    0.17
    ively
    0.17
     towards
    0.15
    lessly
    0.15
    z
    0.15
    istic
    0.15
     instincts
    0.14
    ically
    0.14
    ëĭ¤ê°Ģ
    0.14
    Act Density 0.030%

    No Known Activations