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

    Neuronpedia

    INDEX
    Explanations

    phrases with structured language, possibly indicating formal or persuasive writing

    oai_token-act-pair · gpt-3.5-turbo

    instances of prose and references to bread-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arov
    -0.85
    DERR
    -0.82
    ATES
    -0.72
    ALE
    -0.71
    ARDS
    -0.68
     guiActiveUnfocused
    -0.65
    ered
    -0.64
    IENT
    -0.64
    IELD
    -0.64
    hap
    -0.63
    POSITIVE LOGITS
    ctors
    0.96
     prose
    0.91
    ffer
    0.90
     guiActiveUn
    0.89
    itably
    0.89
    ilk
    0.81
    ly
    0.79
    zai
    0.76
    writer
    0.76
    itable
    0.75
    Act Density 0.009%

    No Known Activations