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

    terms related to directing or guiding actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Joined
    -0.72
    tex
    -0.70
    ylon
    -0.67
    skirts
    -0.63
    aps
    -0.62
    sung
    -0.62
    together
    -0.62
    maker
    -0.61
    iders
    -0.61
    akening
    -0.60
    POSITIVE LOGITS
     toward
    1.20
     towards
    1.16
     attention
    0.88
     inquiries
    0.85
     directed
    0.83
     downwards
    0.81
     energies
    0.79
    irect
    0.79
    eering
    0.78
    nance
    0.77
    Act Density 0.087%

    No Known Activations