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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with question words followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that indicate a sense of community or collective action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ces
    -0.87
    76561
    -0.80
    ooks
    -0.75
    Par
    -0.71
    assembly
    -0.71
    assemb
    -0.68
    ories
    -0.67
    ching
    -0.67
    opens
    -0.65
    yrights
    -0.65
    POSITIVE LOGITS
     succeed
    1.04
     be
    0.95
     accept
    0.92
     continue
    0.92
     concede
    0.89
     abandon
    0.88
     overwrite
    0.87
     tolerate
    0.87
     persist
    0.86
     differ
    0.86
    Act Density 0.051%

    No Known Activations