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

    Neuronpedia

    INDEX
    Explanations

    verbs related to influence and shaping actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to influence and shaping opinions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zik
    -0.66
     Feet
    -0.66
    çĦ
    -0.66
    owler
    -0.65
    esides
    -0.64
    Job
    -0.63
    SourceFile
    -0.63
    psons
    -0.62
    asking
    -0.62
    follow
    -0.62
    POSITIVE LOGITS
     minds
    1.05
     perceptions
    0.94
     ecosystems
    0.82
     atmosp
    0.80
     wills
    0.77
     reality
    0.76
    ulate
    0.75
     sands
    0.75
     levers
    0.73
     society
    0.73
    Act Density 0.247%

    No Known Activations