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

    Neuronpedia

    INDEX
    Explanations

    phrases related to suitability or compatibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to suitability or appropriateness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aura
    -0.97
    yx
    -0.67
    ulhu
    -0.67
     helicop
    -0.67
    dash
    -0.67
    dollar
    -0.65
    eely
    -0.65
    CHA
    -0.65
    antine
    -0.64
    ylum
    -0.64
    POSITIVE LOGITS
     suited
    0.84
     suitable
    0.84
     fit
    0.79
     fitting
    0.76
     candidates
    0.74
     fits
    0.72
    folios
    0.70
    fitting
    0.70
     Dragonbound
    0.66
     substitutes
    0.66
    Act Density 0.025%

    No Known Activations