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

    Neuronpedia

    INDEX
    Explanations

    verbs related to perception or judgment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.63
    amac
    -0.63
    ozo
    -0.63
     narration
    -0.61
    ESSION
    -0.60
    etting
    -0.58
     sob
    -0.57
    rontal
    -0.57
    essions
    -0.57
    earances
    -0.57
    POSITIVE LOGITS
    phas
    1.14
     discriminated
    0.83
     satisfied
    0.78
     insufficient
    0.78
     fit
    0.77
    mand
    0.77
     compelled
    0.76
     disadvantaged
    0.75
     inadequate
    0.74
    poses
    0.74
    Act Density 0.282%

    No Known Activations