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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that imply or insinuate something

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that suggest meaning without explicitly stating it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reds
    -0.74
    gard
    -0.72
    tis
    -0.69
    ouston
    -0.68
    mir
    -0.68
    frey
    -0.67
    vez
    -0.65
    anke
    -0.65
     Ern
    -0.64
    meric
    -0.64
    POSITIVE LOGITS
     imply
    0.88
     inference
    0.85
     implied
    0.83
    icit
    0.81
     infer
    0.78
     assumption
    0.76
     endorsement
    0.75
     guiActiveUn
    0.75
     assumptions
    0.74
    olate
    0.74
    Act Density 0.034%

    No Known Activations