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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    actions related to investigation, planning, and seeking in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritical
    -0.64
    sac
    -0.63
    tes
    -0.63
     afore
    -0.62
    bal
    -0.61
    âĢij
    -0.59
    cia
    -0.59
    ijk
    -0.58
    croft
    -0.58
     preceding
    -0.58
    POSITIVE LOGITS
    irection
    0.66
    IUM
    0.65
    igated
    0.64
    inar
    0.64
     cautiously
    0.64
    igating
    0.63
     Spectre
    0.61
    hani
    0.60
    STD
    0.60
    ependent
    0.60
    Act Density 0.263%

    No Known Activations