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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors or terms related to quality or reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the word "bad"

    np_acts-logits-general · gemini-2.0-flash

    bad reputation, news, and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.56
    ┛
    -0.55
    NonNull
    -0.53
     Thickness
    -0.53
    AddColumn
    -0.53
    __':
    -0.53
    ResumeLayout
    -0.53
    ChangeEvent
    -0.52
    exitRule
    -0.51
    readonly
    -0.50
    POSITIVE LOGITS
    gering
    0.84
     luck
    0.74
    gered
    0.73
     news
    0.72
    mou
    0.72
    dies
    0.71
     habits
    0.69
    minton
    0.69
    die
    0.68
    mouthed
    0.67
    Act Density 0.101%

    No Known Activations