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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing hypothetical scenarios or consequences

    oai_token-act-pair · gpt-3.5-turbo

    conditional and future tense verbs related to potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jam
    -0.64
     Trap
    -0.64
    LinkedIn
    -0.63
    ament
    -0.62
    DAQ
    -0.62
    weed
    -0.61
     monog
    -0.60
    reality
    -0.60
    Times
    -0.58
    ZI
    -0.58
    POSITIVE LOGITS
     be
    0.98
     arrive
    0.90
     also
    0.86
     likewise
    0.85
     doubtless
    0.84
     undoubtedly
    0.83
     derive
    0.82
     furthermore
    0.81
     become
    0.80
     begin
    0.79
    Act Density 0.340%

    No Known Activations