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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or ambiguity regarding future outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ghost
    -0.14
    urt
    -0.14
     naš
    -0.14
    Ë
    -0.14
    escal
    -0.14
     nearest
    -0.13
    yh
    -0.13
     -----------------------------------------------------------------------------↵
    -0.13
     wed
    -0.13
    jom
    -0.13
    POSITIVE LOGITS
     anybody
    0.40
     anyone
    0.39
     Anyone
    0.34
    Anyone
    0.30
     unknown
    0.24
    unknown
    0.22
     UNKNOWN
    0.20
     Unknown
    0.19
    Unknown
    0.19
     beside
    0.18
    Act Density 0.028%

    No Known Activations