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

    Neuronpedia

    INDEX
    Explanations

    phrases related to working processes or mechanisms

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating functionality or operation of systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.66
    xual
    -0.66
    cele
    -0.66
    clad
    -0.64
    gart
    -0.63
    Todd
    -0.63
    Cele
    -0.62
    angular
    -0.61
    va
    -0.59
    verted
    -0.59
    POSITIVE LOGITS
    hops
    1.48
    paces
    1.38
    heet
    1.35
    pace
    1.07
    bench
    1.02
    hift
    0.93
    hirt
    0.91
    ometimes
    0.89
     collabor
    0.85
    esian
    0.82
    Act Density 0.036%

    No Known Activations