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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe the state or condition of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OTHERWISE
    -0.16
    berman
    -0.16
    undy
    -0.15
    ände
    -0.15
    ertas
    -0.15
    rava
    -0.15
    pii
    -0.14
    idis
    -0.14
    lassen
    -0.14
    _advanced
    -0.14
    POSITIVE LOGITS
     fond
    0.21
     generally
    0.18
     creatures
    0.17
     increasingly
    0.17
     notorious
    0.17
     encouraged
    0.17
     taught
    0.16
     sensitive
    0.16
     ke
    0.16
    uman
    0.16
    Act Density 0.137%

    No Known Activations