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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty or speculative scenarios

    oai_token-act-pair · gpt-3.5-turbo

    conditional and modal verbs that discuss possibilities and hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.73
    76561
    -0.67
    iling
    -0.66
    package
    -0.64
    tracking
    -0.63
     Continuing
    -0.63
    Introduced
    -0.62
    oller
    -0.61
    OTA
    -0.60
    noticed
    -0.59
    POSITIVE LOGITS
     raining
    1.05
     beh
    1.01
     happen
    0.89
    iner
    0.82
    etsk
    0.82
     dawn
    0.81
     impossible
    0.74
     happ
    0.73
     happened
    0.73
     unclear
    0.72
    Act Density 0.226%

    No Known Activations