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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or permission

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    forms
    -0.63
    coming
    -0.62
     adolesc
    -0.62
    POL
    -0.60
    comes
    -0.60
    po
    -0.59
    resents
    -0.58
    IDs
    -0.58
    jri
    -0.57
    dri
    -0.57
    POSITIVE LOGITS
     wonder
    1.08
     notice
    1.01
     wondering
    0.92
     wanna
    0.91
     want
    0.91
     prefer
    0.90
     choose
    0.90
    haps
    0.87
     hear
    0.87
     tempted
    0.84
    Act Density 0.042%

    No Known Activations