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

    Neuronpedia

    INDEX
    Explanations

    instances where something transitions from one state to another

    oai_token-act-pair · gpt-3.5-turbo

    the word "from" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perture
    -0.87
    insula
    -0.79
    iosyn
    -0.76
    Mask
    -0.75
    gemony
    -0.73
    sylv
    -0.73
    catentry
    -0.73
    quote
    -0.71
    iquette
    -0.71
    mask
    -0.71
    POSITIVE LOGITS
     afar
    1.05
     whence
    0.81
     abroad
    0.80
     somewhere
    0.80
     scratch
    0.77
     anywhere
    0.74
     nowhere
    0.74
     across
    0.71
     wherever
    0.68
     obscurity
    0.68
    Act Density 0.059%

    No Known Activations