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

    Neuronpedia

    INDEX
    Explanations

    future plans or intentions expressed through the phrase "going to"

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to future intentions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rouse
    -0.90
    Lago
    -0.74
    Decl
    -0.71
    virt
    -0.70
    lag
    -0.66
    gain
    -0.66
    ulu
    -0.63
    rophe
    -0.63
    chemical
    -0.63
    perm
    -0.61
    POSITIVE LOGITS
    ãĥ¼ãĥ«
    0.71
    angered
    0.68
     prob
    0.67
     ðŁij
    0.65
     Peb
    0.65
     Avenger
    0.64
     done
    0.63
    naissance
    0.63
     gonna
    0.61
    idered
    0.61
    Act Density 0.115%

    No Known Activations