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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions involving physical movements and interactions between characters

    oai_token-act-pair · gpt-3.5-turbo

    actions or responses related to visual observation and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.69
    oÄŁ
    -0.67
    efeated
    -0.58
    2017
    -0.58
     decentralized
    -0.57
    ancial
    -0.57
    forestation
    -0.57
    eln
    -0.57
    unity
    -0.57
     discriminated
    -0.57
    POSITIVE LOGITS
     angrily
    0.85
     plaint
    0.85
     quizz
    0.84
     nervously
    0.84
     gloom
    0.78
     gently
    0.76
     grin
    0.75
     puzzled
    0.74
     startled
    0.74
     softly
    0.73
    Act Density 0.527%

    No Known Activations