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

    Neuronpedia

    INDEX
    Explanations

    instances of threats or threatening language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.59
     createSprite
    -0.52
    ColumnHeaders
    -0.51
     createSlice
    -0.49
    ngths
    -0.48
    __":
    -0.45
    ArrowToggle
    -0.42
     protoimpl
    -0.42
     ivelany
    -0.42
    canestro
    -0.42
    POSITIVE LOGITS
     threatening
    0.93
     threaten
    0.85
    threatening
    0.82
     threatens
    0.71
     threatened
    0.71
    Threat
    0.69
     amenaz
    0.65
     amea
    0.65
     amenaza
    0.65
    threat
    0.64
    Act Density 0.128%

    No Known Activations