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

    Neuronpedia

    INDEX
    Explanations

    terms related to instability and instances of related processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SerializedName
    -0.83
    BeginContext
    -0.82
    liosis
    -0.79
    tvguidetime
    -0.79
     cherries
    -0.79
     grecque
    -0.78
    #######
    -0.78
     épar
    -0.77
     Arie
    -0.76
     Diener
    -0.75
    POSITIVE LOGITS
    inst
    1.42
     Inst
    1.41
     inst
    1.38
    Inst
    1.35
    INST
    1.05
     INST
    1.00
     instability
    0.82
     Instability
    0.79
    InjectMocks
    0.74
     Instinct
    0.70
    Act Density 0.007%

    No Known Activations