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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating mathematical definitions or conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SPATH
    -0.52
    ervé
    -0.51
     magari
    -0.50
    ref
    -0.47
    REF
    -0.45
     Arm
    -0.45
    ++
    -0.45
    stead
    -0.45
    vamo
    -0.44
    EndContext
    -0.44
    POSITIVE LOGITS
     صوتيه
    0.84
     الحره
    0.75
     الدولى
    0.73
     nakalista
    0.65
    IntoConstraints
    0.65
    principalTable
    0.62
    ibouti
    0.59
    vdash
    0.59
    WebMethod
    0.59
     hydrothermal
    0.57
    Act Density 0.250%

    No Known Activations