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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and conversational interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andle
    -0.15
    Sleep
    -0.14
    .Unity
    -0.14
    incinn
    -0.14
     TORT
    -0.14
    _SLEEP
    -0.13
    orrh
    -0.13
    宿
    -0.13
     UIControl
    -0.13
     रस
    -0.13
    POSITIVE LOGITS
     approached
    0.27
     approach
    0.26
     strangers
    0.25
     passer
    0.25
     approaches
    0.24
     approaching
    0.24
     Approach
    0.23
    appro
    0.23
     stranger
    0.23
     conversation
    0.23
    Act Density 0.339%

    No Known Activations