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

    Neuronpedia

    INDEX
    Explanations

    occurrences of significant punctuation or formatting cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eters
    -0.16
     Conserv
    -0.15
    gard
    -0.15
    etak
    -0.15
    Tube
    -0.15
    onica
    -0.14
    984
    -0.14
    /sbin
    -0.14
    anes
    -0.14
    owied
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĥĩ
    0.15
    ysa
    0.14
     Mesa
    0.14
    elin
    0.14
    shine
    0.14
     Vend
    0.14
    ãģ£ãģ±
    0.14
    teness
    0.14
    ÑģÑĤв
    0.14
    LEGAL
    0.14
    Act Density 0.035%

    No Known Activations