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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence of restrictions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.78
    BeginContext
    -0.77
    ScopeManager
    -0.76
     Pilate
    -0.73
     Cæsar
    -0.72
    MemoryWarning
    -0.70
     ComVisible
    -0.69
    клопе
    -0.66
    --)
    -0.66
    ConstraintMaker
    -0.66
    POSITIVE LOGITS
    skap
    0.63
     hijas
    0.51
    endal
    0.50
    getDescriptor
    0.49
     existing
    0.48
     I
    0.47
     but
    0.47
    akai
    0.47
     Weiter
    0.45
    issan
    0.45
    Act Density 0.140%

    No Known Activations