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

    Neuronpedia

    INDEX
    Explanations

    verbs related to giving instructions or guidance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "directed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    skirts
    -0.76
    tex
    -0.74
    natureconservancy
    -0.70
    gerald
    -0.66
    iddler
    -0.65
    ylon
    -0.63
    enegger
    -0.63
    urity
    -0.62
    iled
    -0.62
    board
    -0.61
    POSITIVE LOGITS
     toward
    1.15
     towards
    1.10
    ovie
    0.92
    irection
    0.84
     directed
    0.84
    irect
    0.79
    eering
    0.77
     inquiries
    0.77
     blame
    0.75
     downwards
    0.75
    Act Density 0.072%

    No Known Activations