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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating a direction, movement, or leadership towards a specific goal or place

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "headed" indicating direction or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Corpus
    -0.76
    EVA
    -0.72
    rehens
    -0.70
    urity
    -0.70
    Premium
    -0.64
    æѦ
    -0.63
    oret
    -0.60
    ressor
    -0.60
    ional
    -0.60
    Mit
    -0.59
    POSITIVE LOGITS
     headed
    0.95
     nodd
    0.89
     adolesc
    0.81
    heading
    0.76
     heading
    0.75
    pins
    0.74
    canon
    0.73
     nodding
    0.73
    wcs
    0.73
    lander
    0.72
    Act Density 0.006%

    No Known Activations