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

    Neuronpedia

    INDEX
    Explanations

    phrases that express subjective opinions or reviews about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñıг
    -0.15
    ce
    -0.15
    alat
    -0.15
    наÑĤ
    -0.14
    raph
    -0.14
     directly
    -0.13
    ht
    -0.13
    ween
    -0.13
     transition
    -0.13
    yle
    -0.13
    POSITIVE LOGITS
    VarChar
    0.17
    eza
    0.16
    isia
    0.16
    .scalablytyped
    0.16
    _Tis
    0.16
    _Lean
    0.15
    indr
    0.15
    liš
    0.15
    ambia
    0.15
    buie
    0.15
    Act Density 0.106%

    No Known Activations