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

    Neuronpedia

    INDEX
    Explanations

    words associated with different concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate associations or relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intend
    -0.72
    OUT
    -0.70
     helicop
    -0.65
    ²¾
    -0.64
     Bounce
    -0.63
    tein
    -0.63
    umblr
    -0.62
    ciples
    -0.61
     Divide
    -0.61
    pan
    -0.60
    POSITIVE LOGITS
     with
    1.02
    atively
    0.86
    ively
    0.85
    ative
    0.81
    ativity
    0.77
    with
    0.74
     thereto
    0.73
     WITH
    0.73
     With
    0.72
     wi
    0.71
    Act Density 0.072%

    No Known Activations