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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting evaluations or descriptions of the state of the world

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the state of the world or general condition assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ois
    -0.83
    tein
    -0.77
    lees
    -0.69
    rouse
    -0.68
    ricular
    -0.66
    atical
    -0.66
     compares
    -0.65
    ths
    -0.65
    anches
    -0.65
    dB
    -0.63
    POSITIVE LOGITS
     ravaged
    0.83
     stagn
    0.81
     darkened
    0.78
     evolving
    0.77
     warmed
    0.77
     rigged
    0.77
    Thumbnail
    0.76
     fragmented
    0.75
     fucked
    0.74
     tilted
    0.71
    Act Density 0.532%

    No Known Activations