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

    Neuronpedia

    INDEX
    Explanations

    verbs related to exerting pressure or influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to the concept of "pushing" or advancing actions and initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.80
    krit
    -0.65
    Condition
    -0.65
    psons
    -0.65
    mint
    -0.64
    lys
    -0.64
    uster
    -0.63
    namese
    -0.63
    ateur
    -0.63
    enfranch
    -0.62
    POSITIVE LOGITS
     forward
    1.24
     boundaries
    1.18
     aside
    1.17
     buttons
    1.13
    back
    1.11
     back
    1.09
     ahead
    1.06
     onward
    1.03
     harder
    0.98
     forwards
    0.96
    Act Density 0.070%

    No Known Activations