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

    Neuronpedia

    INDEX
    Explanations

    terms related to surprising outcomes or unexpected results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JNIEnv
    -0.66
    featureID
    -0.64
    DrawerToggle
    -0.61
    LookAnd
    -0.61
    CreateMap
    -0.60
     surla
    -0.57
    ResumeLayout
    -0.55
    EndInit
    -0.52
     banques
    -0.52
     NSCoder
    -0.51
    POSITIVE LOGITS
     surprise
    0.76
     surprises
    0.76
     surprising
    0.67
     shocking
    0.66
     reveal
    0.62
    Spoiler
    0.61
    surprise
    0.58
    衝撃
    0.58
     reveals
    0.56
     rivel
    0.56
    Act Density 0.129%

    No Known Activations